virtio/vhost: fixes for 4.2

Bugfixes and documentation fixes. Igor's patch that allows
 users to tweak memory table size is borderline,
 but it does fix known crashes, so I merged it.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJVpBzpAAoJECgfDbjSjVRpQXEIAMEqetqPuRduynjIw2HNktle
 fe/UUhvipwTsAM4R2pmcEl5tW04A/M54RkXN4iVy0rPshAfG3Fh4XTjLmzSGU0fI
 KD6qX8/Zc/+DUWnfe3aUC6jOOrjb7c4xRKOlQ9X8lZgi2M6AzrPeoZHFTtbX34CU
 2kcnv5Sb1SaI/t2SaCc2CaKilQalEOcd59gGjje2QXjidZnIVHwONrOyjBiINUy6
 GzfTgvAje8ZiG6951W3HDwwSfcqXezin27LJqnZgaLCwTCKt2gdQ2MAKjrfP2aVF
 +gX2B4XxcFLutMVx/obsjvA1ceipubyUauRLB3mnO3P5VOj1qbofa2lj4pzQ80k=
 =EKPr
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost fixes from Michael Tsirkin:
 "Bugfixes and documentation fixes.

  Igor's patch that allows users to tweak memory table size is
  borderline, but it does fix known crashes, so I merged it"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  vhost: add max_mem_regions module parameter
  vhost: extend memory regions allocation to vmalloc
  9p/trans_virtio: reset virtio device on remove
  virtio/s390: rename drivers/s390/kvm -> drivers/s390/virtio
  MAINTAINERS: separate section for s390 virtio drivers
  virtio: define virtio_pci_cfg_cap in header.
  virtio: Fix typecast of pointer in vring_init()
  virtio scsi: fix unused variable warning
  vhost: use binary search instead of linear in find_region()
  virtio_net: document VIRTIO_NET_CTRL_GUEST_OFFLOADS

MAINTAINERS

@@ -5899,7 +5899,6 @@ S:	Supported
 F:	Documentation/s390/kvm.txt
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/kvm/
-F:	drivers/s390/kvm/
 
 KERNEL VIRTUAL MACHINE (KVM) FOR ARM
 M:	Christoffer Dall <christoffer.dall@linaro.org>
@@ -10896,6 +10895,15 @@ F:	drivers/block/virtio_blk.c
 F:	include/linux/virtio_*.h
 F:	include/uapi/linux/virtio_*.h
 
+VIRTIO DRIVERS FOR S390
+M:	Christian Borntraeger <borntraeger@de.ibm.com>
+M:	Cornelia Huck <cornelia.huck@de.ibm.com>
+L:	linux-s390@vger.kernel.org
+L:	virtualization@lists.linux-foundation.org
+L:	kvm@vger.kernel.org
+S:	Supported
+F:	drivers/s390/virtio/
+
 VIRTIO GPU DRIVER
 M:	David Airlie <airlied@linux.ie>
 M:	Gerd Hoffmann <kraxel@redhat.com>

drivers/s390/Makefile

@@ -2,7 +2,7 @@
 # Makefile for the S/390 specific device drivers
 #
 
-obj-y += cio/ block/ char/ crypto/ net/ scsi/ kvm/
+obj-y += cio/ block/ char/ crypto/ net/ scsi/ virtio/
 
 drivers-y += drivers/s390/built-in.o
 

drivers/scsi/virtio_scsi.c

@@ -949,7 +949,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 {
 	struct Scsi_Host *shost;
 	struct virtio_scsi *vscsi;
-	int err, host_prot;
+	int err;
 	u32 sg_elems, num_targets;
 	u32 cmd_per_lun;
 	u32 num_queues;
@@ -1009,6 +1009,8 @@ static int virtscsi_probe(struct virtio_device *vdev)
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_T10_PI)) {
+		int host_prot;
+
 		host_prot = SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION |
 			    SHOST_DIF_TYPE3_PROTECTION | SHOST_DIX_TYPE1_PROTECTION |
 			    SHOST_DIX_TYPE2_PROTECTION | SHOST_DIX_TYPE3_PROTECTION;

drivers/vhost/vhost.c

@@ -22,14 +22,20 @@
 #include <linux/file.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/kthread.h>
 #include <linux/cgroup.h>
 #include <linux/module.h>
+#include <linux/sort.h>
 
 #include "vhost.h"
 
+static ushort max_mem_regions = 64;
+module_param(max_mem_regions, ushort, 0444);
+MODULE_PARM_DESC(max_mem_regions,
+	"Maximum number of memory regions in memory map. (default: 64)");
+
 enum {
-	VHOST_MEMORY_MAX_NREGIONS = 64,
 	VHOST_MEMORY_F_LOG = 0x1,
 };
 
@@ -543,7 +549,7 @@ void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
 		fput(dev->log_file);
 	dev->log_file = NULL;
 	/* No one will access memory at this point */
-	kfree(dev->memory);
+	kvfree(dev->memory);
 	dev->memory = NULL;
 	WARN_ON(!list_empty(&dev->work_list));
 	if (dev->worker) {
@@ -663,6 +669,28 @@ int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 }
 EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
+static int vhost_memory_reg_sort_cmp(const void *p1, const void *p2)
+{
+	const struct vhost_memory_region *r1 = p1, *r2 = p2;
+	if (r1->guest_phys_addr < r2->guest_phys_addr)
+		return 1;
+	if (r1->guest_phys_addr > r2->guest_phys_addr)
+		return -1;
+	return 0;
+}
+
+static void *vhost_kvzalloc(unsigned long size)
+{
+	void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+
+	if (!n) {
+		n = vzalloc(size);
+		if (!n)
+			return ERR_PTR(-ENOMEM);
+	}
+	return n;
+}
+
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 {
 	struct vhost_memory mem, *newmem, *oldmem;
@@ -673,21 +701,23 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -EFAULT;
 	if (mem.padding)
 		return -EOPNOTSUPP;
-	if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
+	if (mem.nregions > max_mem_regions)
 		return -E2BIG;
-	newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL);
+	newmem = vhost_kvzalloc(size + mem.nregions * sizeof(*m->regions));
 	if (!newmem)
 		return -ENOMEM;
 
 	memcpy(newmem, &mem, size);
 	if (copy_from_user(newmem->regions, m->regions,
 			   mem.nregions * sizeof *m->regions)) {
-		kfree(newmem);
+		kvfree(newmem);
 		return -EFAULT;
 	}
+	sort(newmem->regions, newmem->nregions, sizeof(*newmem->regions),
+		vhost_memory_reg_sort_cmp, NULL);
 
 	if (!memory_access_ok(d, newmem, 0)) {
-		kfree(newmem);
+		kvfree(newmem);
 		return -EFAULT;
 	}
 	oldmem = d->memory;
@@ -699,7 +729,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		d->vqs[i]->memory = newmem;
 		mutex_unlock(&d->vqs[i]->mutex);
 	}
-	kfree(oldmem);
+	kvfree(oldmem);
 	return 0;
 }
 
@@ -992,17 +1022,22 @@ EXPORT_SYMBOL_GPL(vhost_dev_ioctl);
 static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
 						     __u64 addr, __u32 len)
 {
-	struct vhost_memory_region *reg;
-	int i;
+	const struct vhost_memory_region *reg;
+	int start = 0, end = mem->nregions;
 
-	/* linear search is not brilliant, but we really have on the order of 6
-	 * regions in practice */
-	for (i = 0; i < mem->nregions; ++i) {
-		reg = mem->regions + i;
-		if (reg->guest_phys_addr <= addr &&
-		    reg->guest_phys_addr + reg->memory_size - 1 >= addr)
-			return reg;
+	while (start < end) {
+		int slot = start + (end - start) / 2;
+		reg = mem->regions + slot;
+		if (addr >= reg->guest_phys_addr)
+			end = slot;
+		else
+			start = slot + 1;
 	}
+
+	reg = mem->regions + start;
+	if (addr >= reg->guest_phys_addr &&
+		reg->guest_phys_addr + reg->memory_size > addr)
+		return reg;
 	return NULL;
 }
 

include/uapi/linux/virtio_net.h

@@ -34,6 +34,7 @@
 /* The feature bitmap for virtio net */
 #define VIRTIO_NET_F_CSUM	0	/* Host handles pkts w/ partial csum */
 #define VIRTIO_NET_F_GUEST_CSUM	1	/* Guest handles pkts w/ partial csum */
+#define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */
 #define VIRTIO_NET_F_MAC	5	/* Host has given MAC address. */
 #define VIRTIO_NET_F_GUEST_TSO4	7	/* Guest can handle TSOv4 in. */
 #define VIRTIO_NET_F_GUEST_TSO6	8	/* Guest can handle TSOv6 in. */
@@ -226,4 +227,19 @@ struct virtio_net_ctrl_mq {
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN        1
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX        0x8000
 
+/*
+ * Control network offloads
+ *
+ * Reconfigures the network offloads that Guest can handle.
+ *
+ * Available with the VIRTIO_NET_F_CTRL_GUEST_OFFLOADS feature bit.
+ *
+ * Command data format matches the feature bit mask exactly.
+ *
+ * See VIRTIO_NET_F_GUEST_* for the list of offloads
+ * that can be enabled/disabled.
+ */
+#define VIRTIO_NET_CTRL_GUEST_OFFLOADS   5
+#define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET        0
+
 #endif /* _LINUX_VIRTIO_NET_H */

include/uapi/linux/virtio_pci.h

@@ -157,6 +157,12 @@ struct virtio_pci_common_cfg {
 	__le32 queue_used_hi;		/* read-write */
 };
 
+/* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
+struct virtio_pci_cfg_cap {
+	struct virtio_pci_cap cap;
+	__u8 pci_cfg_data[4]; /* Data for BAR access. */
+};
+
 /* Macro versions of offsets for the Old Timers! */
 #define VIRTIO_PCI_CAP_VNDR		0
 #define VIRTIO_PCI_CAP_NEXT		1

include/uapi/linux/virtio_ring.h

@@ -31,6 +31,9 @@
  * SUCH DAMAGE.
  *
  * Copyright Rusty Russell IBM Corporation 2007. */
+#ifndef __KERNEL__
+#include <stdint.h>
+#endif
 #include <linux/types.h>
 #include <linux/virtio_types.h>
 
@@ -143,7 +146,7 @@ static inline void vring_init(struct vring *vr, unsigned int num, void *p,
 	vr->num = num;
 	vr->desc = p;
 	vr->avail = p + num*sizeof(struct vring_desc);
-	vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__virtio16)
+	vr->used = (void *)(((uintptr_t)&vr->avail->ring[num] + sizeof(__virtio16)
 		+ align-1) & ~(align - 1));
 }
 

net/9p/trans_virtio.c

@@ -704,6 +704,7 @@ static void p9_virtio_remove(struct virtio_device *vdev)
 
 	mutex_unlock(&virtio_9p_lock);
 
+	vdev->config->reset(vdev);
 	vdev->config->del_vqs(vdev);
 
 	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);